
    ^j                     r    d dl mZ ddlmZ ddlmZ ddlmZ  ed      e G d d	e                    Zd	gZ	y
)    )strict   )PreTrainedConfig)RopeParameters)auto_docstringztencent/Youtu-LLM-2B)
checkpointc                   $    e Zd ZU dZdZdgZddddZdgdgfd	d
gd	gfd	gd	gfdZdddddZi Z	dZ
eed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZedz  ed<   d Zeed!<   d"Zedz  ed#<   d"Zeed$<   d%Zeed&<   d'Zeed(<   dZedz  ed)<   d*Zeed+<   d,Zeed-<   dZedz  ed.<   d/Z edz  ed0<   d1Z!ee"e   z  dz  ed2<   d,Z#eed3<   dZ$e%e&z  dz  ed4<   d,Z'edz  ed5<   d6Z(eed7<   d8Z)eez  dz  ed9<   dZ*edz  ed:<    fd;Z+ xZ,S )<YoutuConfiga   
    rope_interleave (`bool`, *optional*, defaults to `True`):
        Whether to interleave the rotary position embeddings.
    embedding_initializer_range (`float`, *optional*):
        The standard deviation of the truncated_normal_initializer for initializing all embedding matrices.

    ```python
    >>> from transformers import YoutuModel, YoutuConfig
    >>> # Initializing a Youtu-LLM-2B style configuration
    >>> configuration = YoutuConfig()
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```youtupast_key_valuescolwiserowwise)zlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnorm	ep_routergrouped_gemmmoe_tp_experts)zlayers.*.mlp.gatez!layers.*.mlp.experts.gate_up_projzlayers.*.mlp.experts.down_projzlayers.*.mlp.expertsi  
vocab_sizei   hidden_sizei   intermediate_size    num_hidden_layers   num_attention_headsnum_key_value_headsi   kv_lora_ranki   Nq_lora_rank@   qk_rope_head_dim   
v_head_dimqk_nope_head_dimsilu
hidden_acti   max_position_embeddingsinitializer_rangegư>rms_norm_epsT	use_cachepad_token_idi  bos_token_idi eos_token_idtie_word_embeddingsrope_parametersrope_interleaveFattention_biasg        attention_dropoutembedding_initializer_rangec                 z   | j                   1| j                  dk7  rdd| j                  z  dz  z  | _         nd| _         | j                  xs d| j                   z  | _        | j                  | j                  | _        | j
                  | j                  z   | _        | j                  | _        t        | (  di | y )Nr   g       @g      @g      ?g{Gz? )r+   r   r6   r    r   r'   r$   qk_head_dimhead_dimsuper__post_init__)selfkwargs	__class__s     x/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/youtu/configuration_youtu.pyr<   zYoutuConfig.__post_init__a   s    !!)1$),d6F6F0F3/N)N&)-&+/+K+K+ksUYUkUkOk(##+'+'?'?D$0043H3HH--''    )-__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planbase_model_ep_planattribute_mapr   int__annotations__r   r   r   r   r    r!   r"   r$   r&   r'   r)   strr*   r+   floatr,   r-   boolr.   r/   r0   listr1   r2   r   dictr3   r4   r5   r6   r<   __classcell__)r?   s   @r@   r
   r
   "   s    J#4"5"+ )"+ &(9:#%568IJ!"_$56 )-;*8 0	 MJK!s!s!!!!L#"Kt"c Jd
 cJ#)S)&*ut|*L%It#L#*#%L#*%+1L#S	/D(1 $$48O^d*T18#'OTD[' ND ,/us{T)/044( (rA   r
   N)
huggingface_hub.dataclassesr   configuration_utilsr   modeling_rope_utilsr   utilsr   r
   __all__r8   rA   r@   <module>rY      sJ   6 / 3 1 # 12J(" J(  3J(Z /rA   